Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2672. Min Range: -8.2672
Max Act: 8.2672. Min Act: -0.1700
Data Index: 4717191 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.6735. Min Act: -0.1700
Data Index: 4589238 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.6422. Min Act: -0.1700
Data Index: 2562578 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.5172. Min Act: -0.1700
Data Index: 3783331 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.4547. Min Act: -0.1700
Data Index: 2663206 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.5172. Min Act: -0.1700
Data Index: 2365253 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.4547. Min Act: -0.1700
Data Index: 2319546 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.4235. Min Act: -0.1700
Data Index: 1390689 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.4547. Min Act: -0.1700
Data Index: 2765242 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.4235. Min Act: -0.1700
Data Index: 5388445 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3922. Min Act: -0.1700
Data Index: 6927968 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3922. Min Act: -0.1700
Data Index: 1430723 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3610. Min Act: -0.1700
Data Index: 3545624 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3610. Min Act: -0.1700
Data Index: 2517926 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3610. Min Act: -0.1700
Data Index: 409502 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3297. Min Act: -0.1700
Data Index: 3911769 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3297. Min Act: -0.1700
Data Index: 3225214 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3297. Min Act: -0.1700
Data Index: 8275806 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.3297. Min Act: -0.1700
Data Index: 2319534 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2672. Min Range: -8.2672
Max Act: 7.2672. Min Act: -0.1700
Data Index: 150113 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19